http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Edge AI based Hybrid Energy Management Systems
Henar Mike O. Canilang(헤나르),Danielle Jaye S. Agron(다니),Angela Caliwag(안젤라),Wansu Lim(임완수) 한국통신학회 2022 한국통신학회 학술대회논문집 Vol.2022 No.2
This paper proposes energy management system (EMS) convergence to edge AI based - applications owing to demands of intelligent applications. This in inline to modern embedded AI based deployment era. In terms of EMS deployment, the hybrid energy management system (HEMS) is an innovation to the conventional battery/capacitor (supercapacitor or ultracapacitor) based management system. The transition to renewable and clean energy resources to prevent global warming paves way to the demand of existing EMS and HEM. This paper presents an approach for energy management and AI convergence paving way for embedded machine learning applications in particular, edge AI based applications. The consideration for the proposed edge AI based HEMS includes IoT specifically, edge/cloud-based coprocessing capability enabling a plethora of hard and soft real time state-of-the-art applications.
Edge AI-based Brain-Computer Interface for Real-time Applications
Henar Mike Canilang,Chigozie Uzochukwu Udeogu,James Rigor Camacho,Erick Valverde,Angela Caliwag,Wansu Lim 대한인간공학회 2021 대한인간공학회 학술대회논문집 Vol.2021 No.11
Objective: This study aims to integrate brain computer interface (BCI) to edge AI devices for real-time EEG signal processing applications. For the specific implementation in this paper, we applied edge AI device-based EEG signal processing for emotion recognition. Background: The emergence of Electroencephalogram (EEG) based applications for intelligent applications is projected to have rapid advancements in the future. The BCI system enables efficient brain signal acquisition. Current intelligent convergence of EEG based applications includes brain signal processing integrated to deep learning models. It is expected that this convergence in intelligent EEG based applications will push through to on-device local processing such as edge AI devices for portability in state-of-the-art applications. The portability and practical usage of these systems in real-world applications could lead to the development and deployment of many other advanced embedded systems for EEG-based applications. Systems that can run locally on the edge without needing to be connected to a mobile network. Edge AI devices are the leading-edge computing platforms that process data locally to overcome the current constraints of IoT application. This paves way to the integration of edge-based processing as the computing paradigm to process and acquire EEG signals. Owing to the current research advancement for both EEG and edge applications, this paper aims to propose one of the many systematic applications of deploying edge-based EEG using a brain computer interface. Method: The input for this edge-based EEG signal processing is through the BCI interfaced to the edge AI device. The edge AI device deployed with a deep learning model for specific applications locally processes the acquired signal. These acquired signals are valuable for training deep learning models to realize practical applications at the edge. The processed EEG signals enable the system response of the system such as rapid emotion recognition. Results: Varying EEG signals were acquired in each of the BCI channels. These brain signals are segmented to different brain signal clusters such as Gamma waves (30㎐ to 100㎐), Beta waves (12㎐ – 30㎐), Alpha waves (7.5㎐ – 12㎐), Theta waves (4㎐-7.5㎐) and Delta waves (0.1㎐-4㎐) which have specific brain wave description. As for EEG emotion recognition applications, these wave signals are essential for efficient and accurate emotion recognition. The alpha, beta, and gamma waves are identified to be the most discriminative frequency ranges to identify emotion. Each of the EEG signal is classified for emotion recognition and identification such as 1) valence, 2) dominance, 3) arousal and 4) liking. High and low responses from these wave signals have corresponding positive, neutral, and negative emotions based on their neural patterns at parietal and occipital sites. Other applications can use the acquired EEG signals thus maximizing the possible application of edge-based EEG signal processing. Conclusion: The local processing of the EEG signal at the edge enables the edge-based EEG system application thus enabling system response and actuation. Edge EEG also enables local and cloud co-processing whereas this maximizes the benefits of the edge computing paradigm. With this co-processing capability, it enables an adaptive and portable real-time EEG signal processing which is a constraint to conventional EEG based emotion recognition system. Application: EEG is a physiological based emotion recognition which proves to be more accurate than conventional non-physiological emotion recognition. Also, with an edge-based EEG application, it enables portability and flexibility in terms of its deployment. This application aims to be a state-of-the-art innovation to existing physiological and non-physiological emotion recognition. Furthermore, this research paper implementation aims to emphasize the vast possible applications of edge-based EEG signal processing to bridge
DNN Power and Energy Consumption Analysis of Edge AI Devices
Henar Mike Canilang,Angela Caliwag,Jonghun Kwon,Wansu Lim 한국통신학회 2021 한국통신학회 학술대회논문집 Vol.2021 No.2
The application of Deep Neural Networks for real-time data processing and AI applications on edge AI devices is developing rapidly. Deep learning models in real-time applications that yields high accuracy proves to consume more power and energy resources. This gives constraints in deploying computation-intensive DNN-based application to edge AI devices due to its limited computational resources. This paper focuses on power consumption and energy consumption analysis of different DNN models deployed to edge AI devices. To show emphasis with the overall power and energy consumption analysis results, a network optimization is applied for comparisons purposes. This bridges the gap between the deployment of complex DNN designs and its effect to the resource constrained edge AI devices.
Edge EEG: Edge AI Device-based EEG Signal Processing for Emotion Recognition
Henar Mike O. Canilang,Ej Miguel Francisco C. Caliwag,Judith Njoku Nyechinyere,Angela C. Caliwag,Wansu Lim 한국통신학회 2021 한국통신학회 학술대회논문집 Vol.2021 No.11
Edge AI devices paves way to portable and state-of-the-art deployment of AI applications using the edge computing paradigm. Owing to the current constraint of internet-of-thing (IoT), edge AI devices bridges the gap for computationally efficient AI deployment on resource constrained portable embedded device applications. Deep neural networks (DNN) enables the plethora of cutting edge AI device applications. DNN is deployed to edge AI devices for intelligent applications such as signal processing and local processing. For processing, an open-source and low-cost platform is utilized for the results verification. In this paper, an edge AI device-based Electroencephalogram (edge EEG) signal processing for compact real-time applications is proposed. The edge EEG is capable of raw EEG signal acquisition, processing data locally and wireless data transmission and receiving. An open-source brain computer-interface platform (OpenBCI) enables the data acquisition which is process and transmitted to the edge AI device. This edge EEG paves way to multitude of intelligent application using brain signals such as for medical, commercial, and industrial applications. Edge EEG is pivotal to the rapidly increasing EEG-based application demand.
Implementation of Emotion Recognition Using Edge-Cloud Computing
Ej Miguel Francisco Caliwag,Henar Mike O. Canilang,안젤라,임완수 한국통신학회 2022 韓國通信學會論文誌 Vol.47 No.3
Emotion recognition systems has been in demand due to its aid in several applications such as health monitoring, workload and drowsiness detection. For these applications, emotion recognition systems require to be deployed on an edge device. For deployment on an edge device, numerous limitations and bottlenecks such as implementation cost, deployment capabilities, and system efficiency affects the performance of the emotion recognition system. That is, emotion recognition on the edge suffers from either low accuracy or high inference time due to the hardware constraints. Hence, several previous studies focus on the deployment of emotion recognition on the edge. Despite that, low accuracy and high inference time still remains an issue. To resolve this, a platform with higher computation capacity must be employed. In this study, we implement an enhanced emotion recognition system by integrating cloud computing platform to the emotion recognition system process, whereby all emotion recognition tasks are performed on the cloud server, can overcome conventional edge device bottlenecks and provide cost-effectiveness, efficient power consumption, and enhanced computing process. Based on the results shown in this study, the proposed system is successful in predicting the emotion of the users in real-time.